Signal detection based on empirical mode decomposition and Teager–Kaiser energy operator and its application to P and S wave arrival time detection in seismic signal analysis

Denoising the hob vibration signal using improved complete ensemble empirical mode decomposition with adaptive noise and noise quantization strategies

A novel denoising method combining complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) and noise quantization strategies is proposed to solve the problem of the noise of the hob vibration signals disturbing the condition monitoring and feature extraction. The vibration signal is decomposed into several intrinsic mode functions (IMFs) and a residual based on CEEMDAN first. Considering that statistical indicators such as correlation coefficient and kurtosis are not effective in the presence of non-Gaussian noises and modulation because they primarily focus on the signal statistical distribution while ignoring the characteristics of the mechanism, a novel index based on the autocorrelation function analysis called periodic modulation for noise assessment (PMNA) is proposed to quantify the noise of IMFs. Further, IMFs are rearranged in the decreasing order of PMNA. A novel threshold joint with IMFs noise assessment (TJINA) varying with the combination of PMNA and the rearranged IMF retrieval is designed, which has advantages in the local smoothness and small fluctuation. On that basis, IMFs are divided into noise domain and signal domain, IMFs in the noise domain are denoised with TJINA and soft threshold function strategies. The proposed method is applied to the simulated signals with different input signal to noise ratios (SNR_in) and two measured gear hobbing vibration signals. The comparison with some state-of-the-art approaches and the ablation experiment reveals that the proposed method performs better in enhancing the effective components and eliminating noise.

End-to-end heart sound segmentation using deep convolutional recurrent network

Heart sound segmentation (HSS) aims to detect the four stages (first sound, systole, second heart sound and diastole) from a heart cycle in a phonocardiogram (PCG), which is an essential step in automatic auscultation analysis. Traditional HSS methods need to manually extract the features before dealing with HSS tasks. These artificial features highly rely on extraction algorithms, which often result in poor performance due to the different operating environments. In addition, the high-dimension and frequency characteristics of audio also challenge the traditional methods in effectively addressing HSS tasks. This paper presents a novel end-to-end method based on convolutional long short-term memory (CLSTM), which directly uses audio recording as input to address HSS tasks. Particularly, the convolutional layers are designed to extract the meaningful features and perform the downsampling, and the LSTM layers are developed to conduct the sequence recognition. Both components collectively improve the robustness and adaptability in processing the HSS tasks. Furthermore, the proposed CLSTM algorithm is easily extended to other complex heart sound annotation tasks, as it does not need to extract the characteristics of corresponding tasks in advance. In addition, the proposed algorithm can also be regarded as a powerful feature extraction tool, which can be integrated into the existing models for HSS. Experimental results on real-world PCG datasets, through comparisons to peer competitors, demonstrate the outstanding performance of the proposed algorithm.

A Study on Determining Time-Of-Flight Difference of Overlapping Ultrasonic Signal: Wave-Transform Network

An ultrasonic sensors system is commonly used to measure the wall thickness of buried pipelines in the transportation of oil and gas. The key of the system is to precisely measure time-of-flight difference (TOFD) produced by the reflection of ultrasonic on the inner and outer surfaces of the pipelines. In this paper, based on deep learning, a novel method termed Wave-Transform Network is proposed to tackle the issues. The network consists of two parts: part 1 is designed to separate the potential overlapping ultrasonic echo signals generated from two surfaces, and part 2 is utilized to divide the sample points of each signal into two types corresponding to before and after the arrival time of ultrasonic echo, which can determine the time-of-flight (TOF) of each signal and calculate the thickness of pipelines. Numerical simulation and actual experiments are carried out, and the results show satisfactory performances.

Arrival-Time Detection in Wind-Speed Measurement: Wavelet Transform and Bayesian Information Criteria

The time-difference method is a common one for measuring wind speed ultrasonically, and its core is the precise arrival-time determination of the ultrasonic echo signal. However, because of background noise and different types of ultrasonic sensors, it is difficult to measure the arrival time of the echo signal accurately in practice. In this paper, a method based on the wavelet transform (WT) and Bayesian information criteria (BIC) is proposed for determining the arrival time of the echo signal. First, the time-frequency distribution of the echo signal is obtained by using the determined WT and rough arrival time. After setting up a time window around the rough arrival time point, the BIC function is calculated in the time window, and the arrival time is determined by using the BIC function. The proposed method is tested in a wind tunnel with an ultrasonic anemometer. The experimental results show that, even in the low-signal-to-noise-ratio area, the deviation between mostly measured values and preset standard values is mostly within 5 μs, and the standard deviation of measured wind speed is within 0.2 m/s.